CN105227971A - The information recommendation method of a kind of hotel TV and system - Google Patents
The information recommendation method of a kind of hotel TV and system Download PDFInfo
- Publication number
- CN105227971A CN105227971A CN201510402089.9A CN201510402089A CN105227971A CN 105227971 A CN105227971 A CN 105227971A CN 201510402089 A CN201510402089 A CN 201510402089A CN 105227971 A CN105227971 A CN 105227971A
- Authority
- CN
- China
- Prior art keywords
- guest
- information
- label
- elementary
- hotel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4665—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving classification methods, e.g. Decision trees
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The information recommendation method of hotel's TV and a system, comprising: the first guest's information obtaining active user from first information source; From first guest's information, extract guest's attribute information and/or guest's behavioural information, generate the elementary label of guest of active user, utilize set guest's model to carry out cluster on elementary for guest label; Label is optimized according to the cluster result acquisition guest that cluster obtains; Optimize label according to guest to mate in content server, obtain corresponding destination service and recommend active user.The present invention also provides corresponding system.The present invention is subscribed after the multipaths such as canalization obtain the information of current guest carried out statistical analysis by client, PMS system, third party, and push corresponding service of goods according to the interest characteristics analyzing the guest obtained, thus make the service of goods of recommendation agree with the interest characteristics of guest exactly, make guest obtain required information on services in time, thus improve the efficiency of acquisition of information.
Description
Technical field
The present invention relates to information recommendation field, particularly, relate to information recommendation method and the system of a kind of hotel TV.
Background technology
Along with the popularization degree of intelligent television is more and more higher, recommendation business as one of value-added service receives the favor of more and more operator, as by distinguishing the current rating content of guest, can accurately for guest recommends its relevant interested program, promote guest to experience, and new interests growth point can be developed accordingly.
Commonplace based on the recommendation of TV programme at present, in hotel industry, Mei Jian hotel all can arrange the TV network of television set and corresponding coupling in hotel room, current TV network is often only to provide the video of some hotel's self manufacture, come to the local conditions and customs of guest place of matchmakers in city, the travel information at sight spot, showplace and so on.In general, first this way of recommendation obtains the custom of guest's TV reception, collection of server to guest watch custom after, carry out corresponding information analysis, in conjunction with preset EPG (electric program menu), TV programme is recommended again, guest is watched meet the TV programme of own interests.
But at hotel industry, often situation can be different, after guest moves in hotel room, place be a brand-new environment, need to obtain a large amount of peripheral informations, often can not meet needs merely for guest's recommending television, guest still need spended time search needs information, be familiar with environment, thus reduce the efficiency of acquisition of information.
Summary of the invention
For defect of the prior art, the object of this invention is to provide information recommendation method and the system of a kind of hotel TV.
For achieving the above object, the technical solution adopted in the present invention is as follows:
An information recommendation method for hotel's TV, comprises the steps:
From first information source, obtain first guest's information of active user, wherein, first guest's information comprises guest identification's information, the PMS system in first information Yuan Shi hotel;
From described first guest's information, extract guest's attribute information and/or guest's behavioural information, generate the elementary label of guest of active user, utilize set guest's model to carry out cluster on elementary for described guest label;
Label is optimized according to the cluster result acquisition guest that cluster obtains;
Optimize label according to described guest to mate in content server, obtain corresponding destination service and recommend described active user.
Also comprise:
Second guest's information of described active user is obtained from the second information source; Described second information source comprise following any one or two kinds of:
-client;
-reservation system;
The elementary label of described guest also comprises the elementary label of guest of the active user of guest's attribute information and/or the guest's behavioural information generation obtained from described second guest's information.
The described method obtaining second guest's information of described active user from the second information source comprises:
Send call instruction to the second information source, wherein, described call instruction comprises described guest identification's information;
Receive the second guest information corresponding with described guest identification's information that the second information source returns.
The elementary label of described guest comprise described guest's attribute information and/or guest's behavioural information, by analyze in guest's feature that described guest's attribute information and/or guest's behavioural information obtain any one or appoint multiple keyword message.
The method that elementary for described guest label utilizes set guest's model to carry out cluster is comprised:
By the target classification of elementary for described guest tag match in set guest's model;
Using the set label in described target classification as the cluster result corresponding to the elementary label of described guest.
The method of set label in described target classification as the cluster result corresponding to the elementary label of described guest is comprised:
Determining the elementary label of described guest and each other degree of association of described target class respectively, as determining that the elementary label of described guest belongs to other probability of each target class respectively, being designated as probability A;
Each set tag match in described target classification is designated as probability B in other probability of described target class;
According to described probability A and described probability B, determine the weighted value of each set label respectively;
Each set label is sorted by weighted value, using the cluster result of the set label of the correspondence before weighted value row as the elementary label of described guest.
Described destination service be according to described guest optimize label mate in content server time, guest is optimized label and retrieves in a search engine as keyword and obtain.
Guest is optimized the method that label retrieves in a search engine as keyword to comprise: in a search engine, in content server, respective services content carries out index according to set content type, forms the vertical engines based on different content classification; When searching for, respectively described guest being optimized label and retrieving in the vertical engines of each content type, obtain corresponding vertical search result respectively.
In the retrieving of search engine: for each content type, the probability that each destination service in this content type is matched with this content type is designated as probability C; The probability C that matching value guest being optimized label and each destination service is multiplied by each destination service corresponding separately respectively obtains product value, and the destination service corresponding to max product value is defined as Search Results.
Described guest is optimized the method that label carries out retrieving in the vertical engines of each content type to comprise:
Described guest is optimized label to mate respectively with the text label of each content type in content server;
Described text label carries out semantic analysis from the text corresponding to the service content to the content type search engine to obtain.
Described semantic analysis is specifically: add up after text is carried out participle, give different weights during statistics to entry structure different in text, judge the text label that respective services content is corresponding in conjunction with weight according to semantic structure.
Described method also comprises:
Obtain the structural order of each menu column offer in the client corresponding to active user;
The described destination service corresponding with each menu column is sent successively to described client according to described structural order.
The present invention also provides the information recommendation system of a kind of hotel TV, comprises as lower device:
First acquisition device: for obtaining first guest's information from first information source, wherein, first guest's information comprises guest identification's information, the PMS system in first information Yuan Shi hotel;
3rd acquisition device: for optimizing label according to first guest's acquisition of information guest;
4th acquisition device: obtain destination service for optimizing label according to guest;
Described 3rd acquisition device comprises as lower device:
5th acquisition device: for obtaining guest's attribute information and/or guest's behavioural information from first guest's information;
First generating apparatus: for generating the elementary label of guest according to guest's attribute information and/or guest's behavioural information;
First clustering apparatus: for utilizing guest's model to carry out cluster on elementary for guest label, obtain cluster result;
First processing unit: optimize label as guest for obtaining the secondary label of guest according to cluster result.
Also comprise the second acquisition device, for obtaining second guest's information according to described guest identification's information from the second information source; For same guest, its first guest information is different information from second guest's information;
Described second information source comprise following any one or two kinds of:
-client;
-reservation system;
Described 3rd acquisition device: also comprise and optimize label according to second guest's acquisition of information guest;
Described 5th acquisition device: also comprise and obtain guest's attribute information and/or guest's behavioural information from second guest's information;
Described second acquisition device comprises as lower device:
First calling device: for sending call instruction to the second information source, wherein, described call instruction comprises described guest identification's information;
First receiving device: for receiving the second guest information corresponding with guest identification's information that the second information source returns according to call instruction.
Described second acquisition device comprises as lower device:
Second calling device: for sending call instruction to the second information source, wherein, described call instruction comprises guest identification's information;
Second receiving system: that the second information source returns according to call instruction with second guest's information that is guest identification's information matches for receiving;
Second guest's information of described coupling comprises: the guest's information corresponding to other guest identification's information be associated with the guest identification's information in call instruction.
Described first generating apparatus comprises as lower device:
First analytical equipment: for analyzing guest's attribute information and/or guest's behavioural information obtains guest's feature;
Second processing unit: for using any one in guest's attribute information, guest's behavioural information and guest's feature or appoint multiple information as the elementary label of guest.
Described first clustering apparatus comprises as lower device:
First coalignment: for by the classification of elementary for guest tag match in guest's model;
3rd processing unit: for using the set label in described classification as the secondary label corresponding to the elementary label of this guest;
4th processing unit: for using described secondary label as the information in cluster result.
Described first clustering apparatus comprises as lower device:
Second coalignment: for by the classification of elementary for guest tag match in guest's model;
5th processing unit: for determining the degree of association of the elementary label of this guest and this classification, as determining that the elementary label of this guest belongs to the probability of this classification, is designated as probability A;
6th processing unit: for using set for each in this classification label as the secondary label corresponding to the elementary label of this guest; Wherein, in this classification, each set tag match is designated as probability B in the probability of this classification;
7th processing unit: for determining the weighted value of each secondary label, wherein, described weighted value equals the product of probability A and probability B;
8th processing unit: for by descending for weighted value sequence, and using secondary label corresponding for some weighted values forward for sequence as the information in cluster result.
Described 4th acquisition device comprises as lower device:
First searcher: to retrieve in a search engine as keyword obtain destination service for guest being optimized label;
In described search engine, each destination service carries out index according to set classifying content, forms the vertical engines based on different content classification; When searching for, respectively guest being optimized label and retrieving in the vertical engines of the classifying content of coupling, obtaining Search Results respectively.
Described first searcher comprises as lower device:
3rd coalignment: mate with each classifying content for guest being optimized label;
9th processing unit: for classifying content the highest for matching value is optimized as with this guest the classifying content that label matches.
Described 3rd coalignment comprises as lower device:
4th coalignment: mate respectively with the text label of each classifying content for guest being optimized label;
Described text label carries out semantic analysis to the text corresponding to the service content of the classifying content in search engine to obtain.
Described first searcher is in the retrieving of search engine:
For each classifying content, the probability that each destination service in this classifying content is matched with this classifying content is designated as probability C;
Matching value guest being optimized label and each destination service is multiplied by each destination service probability C corresponding separately respectively, obtains product value, the destination service corresponding to max product value is defined as Search Results.
Native system also comprises as lower device:
6th acquisition device: for sending destination service to guest.
Described 6th acquisition device comprises as lower device:
7th acquisition device: for obtain guest client in the sequencing of menu column offer;
First dispensing device: for sending the destination service corresponding with the various menu column according to sequencing successively to client.
Compared with prior art, the present invention has following beneficial effect:
1, guest's information that the present invention gathers in hotel industry carries out statistical analysis, and pushes corresponding service of goods according to the interest characteristics analyzing the guest obtained, and makes guest obtain required information on services in time, thus improves the efficiency of acquisition of information.
2, the present invention subscribes by client, PMS system, third party guest's information that the multipaths such as canalization obtain current guest, and guest's information source is abundanter, thus makes the service of goods of recommendation agree with the interest characteristics of guest exactly.
3, the menu setting order that the present invention is corresponding according to client issues described destination service, agree with the operating sequence of terminal, make terminal also can the information on services that issues from server end of buffer memory in time when network state is bad, ensure that the information acquisition efficiency of guest.
Accompanying drawing explanation
By reading the detailed description done non-limiting example with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the overall procedure schematic diagram of method one embodiment provided by the present invention;
Fig. 2 is the general structure schematic diagram of system one embodiment provided by the present invention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.Following examples will contribute to those skilled in the art and understand the present invention further, but not limit the present invention in any form.It should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, some changes and improvements can also be made.These all belong to protection scope of the present invention.
The present invention is based on information recommendation method and system that the television set in hotel and network provide a kind of hotel TV, guest's information that the present invention gathers in hotel industry carries out statistical analysis, and push corresponding service of goods according to the interest characteristics analyzing the guest obtained, make guest obtain required information on services in time, thus improve the efficiency of acquisition of information; And subscribe by client, PMS system, third party guest's information that the multipaths such as canalization obtain current guest, guest's information source is abundanter, thus make the service of goods of recommendation agree with the interest characteristics of guest exactly, make guest obtain required information on services in time, thus improve the efficiency of acquisition of information.
Shown in Fig. 1, the information recommendation method one embodiment overall procedure of hotel provided by the present invention TV, comprises following content:
From first information source, obtain first guest's information of active user, wherein, first guest's information comprises guest identification's information, the PMS system in described first information Yuan Shi hotel;
From described first guest's information, extract guest's attribute information and/or guest's behavioural information, generate the elementary label of guest of active user, utilize set guest's model to carry out cluster on elementary for described guest label;
Label is optimized according to the cluster result acquisition guest that cluster obtains;
Optimize label according to described guest to mate in content server, obtain corresponding destination service and recommend described active user.
When obtaining first guest's information of active user from first information source, the PMS system in first information Yuan Wei hotel, first guest's information comprises calendar information and/or the identity information of guest, and using the identity information of guest as guest identification's information, wherein, identity information comprise name, certificate number, contact method (such as phone number, E-mail address, micro-signal, No. QQ etc.).When current guest check-ins to hotel, the PMS system in hotel will gather first guest's information of current guest, as current guest name, identification card number (passport No.), sex, move in the time, move in room, move in number of days, move in number, contact method, with the name, identification card number etc. of pedestrian.Handle guest and completely moved in formality, when namely representing that guest moves in, then trigger whole information recommendation process, first guest's information according to current guest is mated in content server, the television set display recommendation information that the content recommendation matched all is installed by the room in Mei Jian hotel, according to the triggering of current guest be presented at current guest move in the television set in room.
When extracting guest's attribute information and/or guest's behavioural information from described first guest's information,
Step a: obtain guest's attribute information and/or guest's behavioural information from first guest's information;
Step b: generate the elementary label of guest according to guest's attribute information and/or guest's behavioural information;
Step c: utilize guest's model to carry out cluster on elementary for guest label, obtain cluster result.
Wherein, guest's model, in the set storage of server end, in the present embodiment, carries out the extraction of the information such as attribute, behavior, feature by the user profile in the whole network, trains, obtain guest's model after statistics.
Further, in step b, when generating the elementary label of guest, comprise the steps:
Analysis guest's attribute information and/or guest's behavioural information obtain guest's feature;
Using any one in guest's attribute information, guest's behavioural information and guest's feature or appoint multiple information as the elementary label of guest.
The keyword that preferred term corresponding in comprehensive guest's feature, guest's attribute information and guest's behavioural information are corresponding, sorts according to weight size, using the guest elementary label of the keyword/preferred term before row as current guest.
Preferably, when cluster is carried out to each guest elementary label, perform following steps:
A: by the target classification of elementary for described guest tag match in set guest's model;
B: using the set label in described target classification as the cluster result corresponding to the elementary label of described guest.
According to cluster result obtain the secondary label of guest optimize label as guest time,
Secondary for guest in cluster result label is optimized, the secondary label of guest after optimizing is optimized label as guest.
The present invention carries out the extraction of guest's attribute information and guest's behavioural information to first guest's information, thus obtain guest's feature, using first guest's information and the guest's feature elementary label as this guest, then each elementary label each given categorisation respectively in set guest's model of guest is mated, judge each elementary label respectively with each degree of association of classifying, thus cluster marking is carried out in guest's model, obtain the probability that elementary label belongs to each classification in guest's model, and using the classification of maximum probability as the classification with corresponding elementary tag match.Further, then extract set label from classification, the guest obtaining this guest optimizes label.
According to described guest optimize label mate in content server time, guest is optimized label and retrieves in a search engine as keyword and obtain destination service.
In a search engine, respective services content carries out index according to set classifying content, forms the vertical engines based on different content classification; When searching for, respectively guest being optimized label and retrieving in the vertical engines of the classifying content of coupling, obtaining Search Results respectively.
In the present embodiment, content server provides destination service with the form of search engine for guest optimizes label, optimizes label for keyword retrieve in a search engine, using the Search Results of Corresponding matching as destination service with guest.In this search engine, the respective services content uploaded carries out index by set classifying content, and each classifying content directly can be specified when uploading, and chooses corresponding content classification and directly uploads; Keyword according to index is classified to respective services content, thus is formed based on vertical engines corresponding to different content classification.
With guest optimize label for keyword retrieve in a search engine time, respectively being sorted in the vertical engines of each classifying content belonging to keyword is retrieved, obtain the vertical result of each classification vertical engines respectively, through integrate each classification vertical result, sort laggard row filter, during integration, multiple dimensions such as the hit rate of label can be optimized and integrate by the PV/UV value of the corresponding page of each service content, guest, the vertical result of preset quantity is returned as destination service.
Guest's information that the present invention obtains current guest by client carries out statistical analysis, and push corresponding service of goods according to the interest characteristics analyzing the guest obtained, guest is made to obtain required information on services in time, and guest's information source is abundanter, thus make the service of goods of recommendation agree with the interest characteristics of guest exactly, improve the efficiency of acquisition of information, agree with the operating sequence of terminal.
Corresponding said method, as shown in Figure 2, the general structure of the information recommendation system of hotel provided by the invention TV, comprises as lower device:
First acquisition device: for obtaining first guest's information from first information source, wherein, first guest's information comprises guest identification's information;
Second acquisition device: for according to guest identification's information, obtain second guest's information from the second information source;
3rd acquisition device: for optimizing label according to first guest's information and second guest's acquisition of information guest;
4th acquisition device: obtain destination service for optimizing label according to guest;
6th acquisition device: for sending destination service to guest.
Concrete, the PMS system in first information Yuan Wei hotel, first guest's information comprises calendar information and/or the identity information of guest.Using the identity information of wherein guest as guest identification's information, wherein, identity information comprises name, certificate number, contact method etc.
Second information source comprise following any one or two kinds of:
-client;
-reservation system (such as online tourism website).
Second guest's information comprise in client and/or reservation system following any one or appoint much information:
-operation note;
-browse record;
-subscription information.
Further, the second acquisition device comprises as lower device:
Second calling device: for sending call instruction to the second information source, wherein, call instruction comprises guest identification's information;
Second receiving system: that the second information source returns according to call instruction with second guest's information that is guest identification's information matches for receiving; Comprise: the guest's information corresponding to other guest identification's information be associated with the guest identification's information in call instruction, be associated comprise following any one or appoint multiple incidence relation:
-relatives;
-region;
-community;
-vehicle-carried order of classes or grades at school;
-binding;
-primary and secondary account.
Further, the 3rd acquisition device comprises as lower device:
5th acquisition device: for obtaining guest's attribute information and/or guest's behavioural information from first guest's information and second guest's information;
First generating apparatus: for generating the elementary label of guest according to guest's attribute information and/or guest's behavioural information;
First clustering apparatus: for utilizing guest's model to carry out cluster on elementary for guest label, obtain cluster result;
First processing unit: optimize label as guest for obtaining the secondary label of guest according to cluster result.
Wherein, the first generating apparatus comprises as lower device:
First analytical equipment: for analyzing guest's attribute information and/or guest's behavioural information obtains guest's feature;
Second processing unit: for using any one in guest's attribute information, guest's behavioural information and guest's feature or appoint multiple information as the elementary label of guest.
Wherein, the first clustering apparatus passes through comprised to perform process to the elementary label of each guest as lower device:
Second coalignment: for by the target classification of elementary for this guest tag match in guest's model;
5th processing unit: for determining other degree of association of this target class in the elementary label of this guest and guest's model, belonging to other probability of this target class as the elementary label of this guest, being designated as probability A;
6th processing unit: for using each the set label in this target classification as the secondary label corresponding to the elementary label of this guest; Wherein, in this target classification, each set tag match is designated as probability B in other probability of this target class;
7th processing unit: for determining the weighted value of each secondary label, this weighted value equals the product of probability A and probability B;
8th processing unit: for using secondary label corresponding for some weighted values forward in descending for weighted value sequence as the information in cluster result.
Further, the 4th acquisition device comprises as lower device:
First searcher: to retrieve in a search engine as keyword obtain destination service for guest being optimized label.
In a search engine, each destination service carries out index according to set classifying content, forms the vertical engines based on different content classification; When searching for, respectively guest being optimized label and retrieving in the vertical engines of the classifying content of coupling, obtaining Search Results respectively.
First searcher obtains by following comprised device the classifying content that guest optimizes tag match:
3rd coalignment: mate with each classifying content for guest being optimized label;
9th processing unit: for classifying content the highest for matching value is optimized as with this guest the classifying content that label matches.
Wherein, described 3rd coalignment comprises as lower device:
4th coalignment: mate respectively with the text label of each classifying content for guest being optimized label;
Wherein, semantic analysis is carried out to the text corresponding to the service content of the classifying content in search engine, obtains the text label corresponding with classifying content.
In the retrieving of search engine: for each classifying content, the probability that each destination service in this classifying content is matched with this classifying content is designated as probability C; The probability C that matching value guest being optimized label and each destination service is multiplied by each destination service corresponding separately respectively obtains product value, and the destination service corresponding to max product value is defined as Search Results.
Further, the 6th acquisition device comprises as lower device:
7th acquisition device: for obtain guest client in the sequencing of menu column offer;
First dispensing device: for sending the destination service corresponding with the various menu column according to sequencing successively to client.
First dispensing device sends to the client of guest the destination service setting quantity.
In a change case, the second acquisition device comprises as lower device:
First calling device: for sending call instruction to the second information source, wherein, call instruction comprises guest identification's information;
First receiving device: for receiving the second guest information corresponding with guest identification's information that the second information source returns according to call instruction.
In a change case, the first clustering apparatus passes through comprised to perform process to the elementary label of each guest as lower device:
First coalignment: for by the classification of elementary for this guest tag match in guest's model;
3rd processing unit: for using the secondary label of the set label in this classification as guest corresponding to the elementary label of this guest;
4th processing unit: for using secondary label as the information in cluster result.
The information recommendation system of hotel provided by the present invention TV, is realized by the information recommendation method of hotel provided by the present invention TV, and information recommendation method one embodiment of hotel provided by the present invention TV comprises the steps:
Step S1: the first guest's information obtaining active user from first information source, wherein, first guest's information comprises guest identification's information, the PMS system in described first information Yuan Shi hotel;
Step S2: the second guest's information obtaining described active user from the second information source; Described second information source comprises client and/or website;
Step S3: extract guest's attribute information and/or guest's behavioural information from described first guest's information and described second guest's information, generates the elementary label of guest of active user, utilizes set guest's model to carry out cluster on elementary for described guest label;
Step S4: optimize label according to the cluster result acquisition guest that cluster obtains;
Step S5: optimize label according to described guest and mate in content server, obtains corresponding destination service and recommends described active user.
Wherein, in step S1, the PMS system in first information Yuan Wei hotel, first guest's information comprises calendar information and/or the identity information of guest, and using the identity information of guest as guest identification's information, wherein, identity information comprise name, certificate number, contact method (such as phone number, E-mail address, micro-signal, No. QQ etc.).When current guest check-ins to hotel, the PMS system in hotel will gather first guest's information of current guest, as current guest name, identification card number (passport No.), sex, move in the time, move in room, move in number of days, move in number, contact method, with the name, identification card number etc. of pedestrian.Handle guest and completely moved in formality, when namely representing that guest moves in, then trigger whole information recommendation process, first guest's information according to current guest is mated in content server, the television set display recommendation information that the content recommendation matched all is installed by the room in Mei Jian hotel, according to the triggering of current guest be presented at current guest move in the television set in room.
In step S2, the second information source comprises Multiple Information Sources: client, website, and wherein, client can be the client in hotel guest room, also can be the client of guest individual; Website can be OTA (OnlineTravelAgent, online tourism society) website, also can be the third party's website with the cooperation of OTA website, OTA website and/or third party's website are when current guest operates, by browsing information and the operation information of the guest of web log file record, as second guest's information.
Second guest's information comprises the much information in client and/or website: operation note, browse record, subscription information.Such as, the intelligent television client enterprising line operate of guest in hotel and browsing, then can gather Operation Log corresponding to this intelligent television client and/or travel log, extract log content corresponding in Operation Log and/or travel log, and log content is analyzed, keyword analysis extraction obtained is as second guest's information, particularly, second guest's information can be by recording each page and the corresponding time of staying in intelligent television that guest checks respectively, the each menu option triggered and corresponding menu entries, add up each page and the corresponding time of staying respectively, the frequency of operation of each menu entries, extract content of pages under menu option in the forward page of rank and the page time of staying and content, and press each part (title in content of pages, subtitle, text) weights statistics keyword, using keyword as second guest's information.
Again such as, guest OTA website or with third party's website of OTA website cooperation in conduct interviews and operate, access log, Operation Log can be obtained from the server of OTA website or third party's website, therefrom obtain browsing information and operation information, and analytic statistics is carried out to browsing information and content of pages corresponding to operation information, extract according to the result of analytic statistics and obtain keyword and like preference as second guest's information with what characterize guest.The station system that website can also be restaurant's Ticket booking system, ticket booking system, film seat reservation system, taxi reservation system, other PMS system etc. can obtain more guest's information.
Again such as, the use record of internet records and each APP can also be extracted from the smart mobile phone of current guest, extract and browse address and Webpage content and keyword thereof, the daily record etc. that the order that current guest uses APP to carry out makes a reservation for, download, produce when operating APP, from the server of APP and mobile browser, obtain corresponding log information, extract keyword by analysis afterwards as second guest's information.
Preferably, hotel's client comprises the intelligent TV set in the room being arranged on Mei Jian hotel, intelligent TV set is associated by the mode such as Quick Response Code or identifying code with the smart mobile phone of guest, when guest is by smart mobile phone remote-controlled intelligent TV, the remote control command that the smart mobile phone that server is received by intelligent TV set sends reads Operation Log corresponding to current guest and/or travel log, according to the operation note of current guest when RTV remote television with browse record, binding operation record and the interest browsing record analysis current guest, by operation note with to browse in record corresponding content of pages and carry out analytic statistics, according to keyword corresponding to analytic statistics as second guest's information.Same, the content of text etc. that in mobile phone A PP, each page and the corresponding time of staying, the frequency of operation of each actions menu entry, guest input can be added up respectively, according to each content of text statistics keyword, using keyword as second guest's information.
When after first guest's information corresponding from the one or more current guest collected respectively in the hotel's client in hotel guest room, PMS system, website, smart mobile phone etc. and second guest's information, respectively information conversion is carried out to first guest's information and second guest's information, be integrated into guest's information of consolidation form, thus comprehensive guest's information can be obtained, to improve the accuracy rate for the service of this guest's exemplary application.
Guest as one " American of 39 years old " have subscribed to moving in of Beijing hotel from ctrip.com, after hotel check-ins, the access log of this guest of extract real-time in the third party's website such as OTA website and Baidu's tourism comprising ctrip.com, obtain the information such as dining room of tourism of Beijing attack strategy that this guest of nearest a period of time browses in OTA website, hobby, according to the operation note of website with browse content of pages corresponding in record and carry out analytic statistics, according to keyword corresponding to analytic statistics as second guest's information.Further, the access log of this guest's mobile phone at particular type APP can also be extracted, as its moved in which type of hotel, the take-away of being which kind of type etc., the content of text corresponding according to access log carries out analytic statistics, according to keyword corresponding to analytic statistics as second guest's information; Can also obtain its PMS information in other hotels, as ordered which type of service etc. before him in hotel, the content of text corresponding according to PMS information carries out analytic statistics, according to keyword corresponding to analytic statistics as second guest's information; Again further, the second guest's information obtaining current guest can also be combined from multiple second information source, as extracted the ticketing information that this guest carries out in sale of ticket website performing from the ticketing website in website, obtain date and the place of this performance, this guest can also be obtained at what date and time, to which destination get off by taxi APP from smart mobile phone, which humane classics of passage in transit etc. information, content of text according to correspondence carries out analytic statistics, according to keyword corresponding to analytic statistics as second guest's information.Be consolidation form by these guest's information integration, Overall Acquisition guest's information of current guest.
Further, step S2 also can comprise the steps:
Step S2.1B: send call instruction to the second information source, wherein, described call instruction comprises guest identification's information of the current guest obtained from first information source;
Step S2.2B: according to call instruction, return second guest's information with guest identification's information matches by the second information source, second guest's information comprises: the guest's information corresponding to other guest identification's information be associated with the guest identification's information in call instruction.Be associated and comprise following multiple incidence relation:
-relatives;
-region;
-community;
-vehicle-carried order of classes or grades at school;
-binding;
-primary and secondary account.
Wherein, the identity information of current guest uniquely can be determined by guest identification's information (such as passport number), the guest identification information corresponding according to current guest carries out information searching respectively in each second information source, thus the guest identification's information according to current guest in each second information source finds corresponding second guest's information respectively.
As preference, in the second information source, the guest's information corresponding to other guest be associated with guest identification's information of this guest can also be comprised.Such as in online tourism website, for the individual as the hotel guest moved in, in its history predetermined information in the server stores of online tourism website or current predetermined information, also probably contain the relevant information of its spouse and children.Preference is liked by the collective that the information of this guest and this relevant information constitute this family, can reflect collective's trip purpose of guest more accurately; Preference is liked by the collective downloading current guest place family corresponding from online tourism website, this collective is liked preference finds corresponding second guest's information respectively as guest identification's information of current guest.
In more example, the relevant information of the subcard holder of guest's credit card can also be obtained in the information system of financial institution; The relevant information of other guest of colony or working group described in this guest can also be found in the information system of forum or micro-letter group, like preference with what meet this grouped population; Can also from the information on airport provide to obtain when this guest arrives Beijing take advantage of the relevant information of the same airline passengers of flight, etc.Preference is liked by the collective that so just can download current guest place family corresponding from corresponding website, realize the second guest's information improving this guest from the angle of colony, like that preference finds corresponding second guest's information respectively as guest identification's information of current guest by this collective, like preference with what embody this guest comprehensively.
Further, step S3 comprises the steps:
Step S3.1: obtain guest's attribute information and/or guest's behavioural information from first guest's information and second guest's information;
Step S3.2: generate the elementary label of guest according to guest's attribute information and/or guest's behavioural information;
Step S3.3: utilize guest's model to carry out cluster on elementary for guest label, obtain cluster result.
Wherein, guest's model is in the set storage of server end, in the present embodiment, by in the whole network respectively by multiple second information sources such as client, PMS system, reservation systems, the first guest's information collected in history and second guest's information are carried out the extraction of the information such as attribute, behavior, feature, train after statistics, obtain guest's model.Preferably, guest's model comprises multiple set classification, wherein, multiple set label is comprised respectively in each classification, these classification and set label can be preset by experience and obtain, and obtain after also can carrying out text analyzing by the corpus in guest's model according to the frequency of occurrences, weight through training.
Further, in step S3.2, when generating the elementary label of guest, comprise the steps:
Step S3.2.1: analysis guest's attribute information and/or guest's behavioural information obtain guest's feature;
In the present embodiment, guest's attribute information, guest's behavioural information are analyzed, extract keyword wherein, and in set knowledge base, carry out analysis coupling to extracting the keyword obtained respectively, respectively text analyzing is carried out to knowledge content corresponding in knowledge base, filter is carried out in each preferred term unification obtained weigh and weights evaluation, extract weights and be greater than the preferred term of given threshold as guest's feature;
Step S3.2.2: using any one in guest's attribute information, guest's behavioural information and guest's feature or appoint multiple information as the elementary label of guest.
The keyword that preferred term corresponding in comprehensive guest's feature, guest's attribute information and guest's behavioural information are corresponding, sorts according to weight size, using the guest elementary label of the keyword/preferred term before row as current guest.
Preferably, in step S3.3, when cluster is carried out to each guest elementary label, perform following steps:
A: by the target classification of elementary for described guest tag match in set guest's model;
In the present embodiment, guest's model has multiple target classification, each target classification respectively respective to should other audience of target class for the probability numbers of some feature, when elementary for the guest of current guest label is mated in guest's model, respectively elementary for guest label is mated together with the secondary label that the near synonym of its correspondence are set with each feature under each target classification, using in target classification, the match is successful the corresponding probability numbers sum of secondary label as the elementary label of this guest and other degree of association of this target class.
B: using the set label in described target classification as the cluster result corresponding to the elementary label of described guest.
Determining the elementary label of described guest and each other degree of association of described target class respectively, as determining that the elementary label of described guest belongs to other probability of each target class respectively, being designated as probability A; Probability A represents that the elementary label of a guest belongs to other probability of certain target class;
Set secondary tag match each in target classification is designated as probability B in other probability of described target class; Probability B represents each secondary label and other matching degree of corresponding target class;
According to described probability A and described probability B, in the present embodiment, described weighted value equals the product of probability A and probability B, determines the weighted value of each secondary label respectively.In other embodiments, the mode that can also be weighted summation by constant calculates weighted value, thus the weighted value of each secondary label of adjustment gained flexibly.
All secondary label corresponding for each target classification is sorted by weighted value, using the cluster result of the secondary label of the correspondence before weighted value row as the elementary label of described guest.
Cluster result illustrates audience characteristic of correspondence belonging to the elementary label of guest, and in corresponding cluster result, set secondary label can belong to multiple target classification.
In step S4, obtain the secondary label of guest according to cluster result and optimize label as guest.
Secondary for guest in cluster result label being optimized, as filtered heavily, preferred etc., the secondary label of guest after optimizing being optimized label as guest.
The present invention carries out the extraction of guest's attribute information and guest's behavioural information to first guest's information and second guest's information, thus obtain guest's feature, by first guest's information, second guest's information, guest's feature is as the elementary label of this guest, the elementary label of a such as guest is " male sex ", " number of visits of tourism natural scenic spot webpage is more ", " have purchased charge garment ", " backpacker ", wherein, elementary label " male sex " is first guest's information from hotel PMS system, elementary label " number of visits of tourism natural scenic spot webpage is more ", " have purchased charge garment " and be second guest's information from guest's mobile phone browser, " backpacker " guest's feature for going out according to first guest's information and second guest's information extraction.
Then each elementary label each given categorisation respectively in set guest's model of guest is mated, judge each elementary label respectively with each degree of association of classifying, thus cluster marking is carried out in guest's model, obtain the probability that elementary label belongs to each classification in guest's model, and using the classification of maximum probability as the classification with corresponding elementary tag match.Further, then extract set label from classification, the guest obtaining this guest optimizes label.
Such as, the attribute information of the current guest of extraction and elementary label corresponding to behavioural information are " 40 years old ", " people ", " American " (extracting in PMS system), " OTA reservation ", " oxtail soup ", " century Tan Fu " (extraction of OTA system), " take-away wine ", " take-away Pizza " (cell-phone customer terminal extraction), obtaining elementary label after mating in guest's model with matching separately classify and the situation of matching probability is " middle aged-95% ", " American-European-90% ", " high heat food-80% ", " the good dining room-60% of environment ", " network intelligent-90% ", " zoo-5% ", " cross-talk-10% ", secondary label " middle high price " corresponding in classifying in " middle age ", " SPA ", secondary label " love wine " set in " America and Europe " classification, " Christian religion ", " western-style food ", secondary label " Pizza " set in " high heat food " classification, " fried chicken ", " cola ", set secondary label " San Litun " corresponding in " the good dining room of environment " classification, " leopard ", the set secondary label " wifi " in " network intelligent " classification, " on-line payment " combines corresponding matching probability respectively and mates, such as, in the present embodiment, the matching probability of elementary label for classification is multiplied with each self-corresponding probability score in this classification of each secondary label in this classification respectively, obtain the probability score of each secondary label, then by " SPA ", " San Litun ", " Christian religion ", the secondary label that " western-style food " equiprobability score value is higher optimizes label as guest.
Further, step S5 comprises the steps:
Step S5.1: guest is optimized label and retrieve in a search engine as keyword and obtain destination service.
In a search engine, respective services content carries out index according to set classifying content, forms the vertical engines based on different content classification; When searching for, respectively guest being optimized label and retrieving in the vertical engines of the classifying content of coupling, obtaining Search Results respectively.
In the present embodiment, content server provides destination service with the form of search engine for guest optimizes label, optimizes label for keyword retrieve in a search engine, using the Search Results of Corresponding matching as destination service with guest.In this search engine, the respective services content uploaded carries out index by set classifying content, each classifying content directly can be specified when uploading, choose corresponding content classification directly to upload, also can be obtained by the keyword of index, specify when respective services content can be uploaded in the keyword of index, or obtain after being analyzed by the content of text uploaded, keyword according to index is classified to respective services content, thus is formed based on vertical engines corresponding to different content classification.
With guest optimize label for keyword retrieve in a search engine time, respectively being sorted in the vertical engines of each classifying content belonging to keyword is retrieved, obtain the vertical result of each classification vertical engines respectively, through integrate each classification vertical result, sort laggard row filter, during integration, multiple dimensions such as the hit rate of label can be optimized and integrate by the PV/UV value of the corresponding page of each service content, guest, the vertical result of preset quantity is returned as destination service.
Wherein, in preference, obtain the classifying content that guest optimizes tag match as follows:
Step I 1: guest is optimized label and mate with each classifying content;
Step I 2: then classifying content the highest for matching value is optimized as with this guest the classifying content that label matches.
Wherein, step I 1 comprises the steps:
Step I 1.1: guest is optimized label and mate respectively with the text label of each classifying content; Semantic analysis is carried out to the text corresponding to the service content of the classifying content in search engine, obtains the text label corresponding with classifying content.Particularly, by content server, text corresponding for the respective services content of crawl is carried out semantic analysis, add up after carrying out participle by text, give different weights to entry structure different in text during statistics, if classifying content is high weight, title weight is middle weight, body part is low weight etc., judge according to semantic structure the text label that respective services content is corresponding in conjunction with weight, and added up by text label, the service content of serving with the objectives is corresponding stored respectively.
In the retrieving of search engine:
For each classifying content, the probability that each destination service in this classifying content is matched with this classifying content is designated as probability C;
The probability C that matching value guest being optimized label and each destination service is multiplied by each destination service corresponding separately respectively obtains product value, and the destination service corresponding to max product value is defined as Search Results.
As above in example, it is " SPA ", " San Litun ", " Christian religion ", " western-style food " that the guest of guest optimizes label, guest is optimized in each classified service of the search engine of label in content server and carry out search coupling, optimize the destination service of SPA guild hall as " service for life " class choosing local hotel in the vertical engines that label " SPA " classifies in " service for life " according to guest; The destination service of western-style restaurant as " food and drink " class choosing this hotel in the vertical engines that label " western-style food " classifies in " food and drink " is optimized according to guest; The destination service of certain favorable comment bar as " amusement " class choosing three li of villages in the vertical engines that label " San Litun " classifies in " amusement " is optimized according to guest; The Wang Fu Jing Church that ranks the first in the vertical engines that label " Christian religion " classifies in " tourist attractions " destination service as " tourist attractions " class is optimized according to guest.
Step S5.2: obtain corresponding destination service and recommend described active user.Such as, the destination service of correspondence can be issued to current guest the intelligent TV set of moving in room show to guest.Comprise:
Obtain the structural order of each menu column offer in the client corresponding to active user;
The described destination service corresponding with each menu column is sent successively to described client according to described structural order.
Particularly, when destination service being issued to client (such as television set or mobile phone), read the menu setting structure that client is corresponding, according to the structural order that described client correspondence is arranged, namely the column rank of menu setting issues destination service corresponding to current guest.Destination service as corresponding in the first add-in in first download menu, then order is set by the add-in in menu and successively downloads corresponding destination service, content recommendation corresponding under making guest preferentially see the column formerly shown in the client, avoid when the bad grade of network condition is abnormal, after guest opens terminal, the corresponding the first column of menu has not downloaded the complete situation of destination service yet.
As above in example, be arranged on the television set of hotel room, respectively the destination service that " service for life ", " food and drink ", " amusement " and " tourist attractions " are respectively classified successively is loaded by the order of menu setting, show respectively: the SPA guild hall in hotel, the western-style restaurant in hotel, certain favorable comment bar in three li of villages and the data entries of Wang Fu Jing Church, corresponding destination service information is shown afterwards according to the triggering of current guest, thus pushed the service of goods agreed with mutually with current guest " American of 39 years old ", make guest obtain required information on services in time.
The present invention passes through client, PMS system, guest's information that third party subscribes the multipath acquisition current guest such as canalization carries out statistical analysis, and push corresponding service of goods according to the interest characteristics analyzing the guest obtained, the menu setting order corresponding according to client issues described destination service, guest is made to obtain required information on services in time, and guest's information source is abundanter, thus make the service of goods of recommendation agree with the interest characteristics of guest exactly, improve the efficiency of acquisition of information, agree with the operating sequence of terminal, make terminal also information on services of issuing from server end of buffer memory in time when network state is bad.
Those skilled in the art will know that, except realizing except system provided by the invention and each device thereof in pure computer readable program code mode, system provided by the invention and each device thereof can be made to realize identical function with the form of gate, switch, application-specific integrated circuit (ASIC), programmable logic controller (PLC) and embedded microcontroller etc. by method step being carried out programming in logic completely.So system provided by the invention and every device thereof can be considered to a kind of hardware component, and to the structure that also can be considered as the device realizing various function in hardware component comprised in it; Also the device being used for realizing various function can be considered as not only can be implementation method software module but also can be structure in hardware component.
Above specific embodiments of the invention are described.It is to be appreciated that the present invention is not limited to above-mentioned particular implementation, those skilled in the art can make a variety of changes within the scope of the claims or revise, and this does not affect flesh and blood of the present invention.When not conflicting, the feature in the embodiment of the application and embodiment can combine arbitrarily mutually.
Claims (18)
1. an information recommendation method for hotel's TV, is characterized in that, comprises the steps:
From first information source, obtain first guest's information of active user, wherein, first guest's information comprises guest identification's information, the PMS system in described first information Yuan Shi hotel;
From described first guest's information, extract guest's attribute information and/or guest's behavioural information, generate the elementary label of guest of active user, utilize set guest's model to carry out cluster on elementary for described guest label;
Label is optimized according to the cluster result acquisition guest that cluster obtains;
Optimize label according to described guest to mate in content server, obtain corresponding destination service and recommend described active user.
2. the information recommendation method of hotel according to claim 1 TV, is characterized in that, also comprise:
Second guest's information of described active user is obtained from the second information source; Described second information source comprise following any one or two kinds of:
-client;
-website;
The elementary label of described guest also comprises the elementary label of guest of the active user of guest's attribute information and/or the guest's behavioural information generation obtained from described second guest's information.
3. the information recommendation method of hotel according to claim 2 TV, is characterized in that, the described method obtaining second guest's information of described active user from the second information source comprises:
Send call instruction to the second information source, wherein, described call instruction comprises described guest identification's information;
Receive the second guest information corresponding with described guest identification's information that the second information source returns.
4. the information recommendation method of hotel according to claim 1 TV, it is characterized in that, the elementary label of described guest comprise described guest's attribute information and/or guest's behavioural information, by analyze in guest's feature that described guest's attribute information and/or guest's behavioural information obtain any one or appoint multiple keyword message.
5. the information recommendation method of the hotel's TV according to claim 1 or 4, is characterized in that, the method that elementary for described guest label utilizes set guest's model to carry out cluster is comprised:
By the target classification of elementary for described guest tag match in set guest's model;
Using the set label in described target classification as the cluster result corresponding to the elementary label of described guest.
6. the information recommendation method of hotel according to claim 5 TV, is characterized in that, the method for the set label in described target classification as the cluster result corresponding to the elementary label of described guest is comprised:
Determining the elementary label of described guest and each other degree of association of described target class respectively, as determining that the elementary label of described guest belongs to other probability of each target class respectively, being designated as probability A;
Each set tag match in described target classification is designated as probability B in other probability of described target class;
According to described probability A and described probability B, determine the weighted value of each set label respectively;
Each set label is sorted by weighted value, using the cluster result of the set label of the correspondence before weighted value row as the elementary label of described guest.
7. the information recommendation method of hotel according to claim 1 TV, it is characterized in that, described destination service be according to described guest optimize label mate in content server time, described guest is optimized label and in set search engine, carries out retrieval as keyword and obtain.
8. the information recommendation method of hotel according to claim 7 TV, it is characterized in that, describedly described guest is optimized the method that label carries out retrieving as keyword in set search engine and comprise: in a search engine, in content server, respective services content carries out index according to set content type, forms the vertical engines based on different content classification; When searching for, respectively described guest being optimized label and retrieving in the vertical engines of each content type, obtain corresponding vertical search result respectively.
9. the information recommendation method of hotel according to claim 8 TV, is characterized in that, described guest is optimized the method that label carries out retrieving in the vertical engines of each content type and comprises:
Described guest is optimized label to mate respectively with the text label of each content type in content server;
Described text label carries out semantic analysis from the text corresponding to the service content to the content type search engine to obtain.
10. the information recommendation method of hotel according to claim 1 TV, is characterized in that, described method also comprises:
Obtain the structural order of each menu column offer in the client corresponding to active user;
The described destination service corresponding with each menu column is sent successively to described client according to described structural order.
The information recommendation system of 11. 1 kinds of hotel's TVs, is characterized in that, comprises as lower device:
First acquisition device: for obtaining first guest's information from first information source, wherein, first guest's information comprises guest identification's information, the PMS system in first information Yuan Shi hotel;
3rd acquisition device: for optimizing label according to first guest's acquisition of information guest;
4th acquisition device: obtain destination service for optimizing label according to guest;
Described 3rd acquisition device comprises as lower device:
5th acquisition device: for obtaining guest's attribute information and/or guest's behavioural information from first guest's information;
First generating apparatus: for generating the elementary label of guest according to guest's attribute information and/or guest's behavioural information;
First clustering apparatus: for utilizing guest's model to carry out cluster on elementary for guest label, obtain cluster result;
First processing unit: optimize label as guest for obtaining the secondary label of guest according to cluster result.
The information recommendation system of 12. hotel according to claim 11 TVs, is characterized in that, also comprise the second acquisition device, for obtaining second guest's information according to described guest identification's information from the second information source; For same guest, its first guest information is different information from second guest's information;
Described second information source comprise following any one or two kinds of:
-client;
-reservation system;
Described 3rd acquisition device: also comprise and optimize label according to second guest's acquisition of information guest;
Described 5th acquisition device: also comprise and obtain guest's attribute information and/or guest's behavioural information from second guest's information.
The information recommendation system of 13. hotel according to claim 12 TVs, is characterized in that, described second acquisition device comprises as lower device:
First calling device: for sending call instruction to the second information source, wherein, described call instruction comprises described guest identification's information;
First receiving device: for receiving the second guest information corresponding with guest identification's information that the second information source returns according to call instruction.
The information recommendation system of 14. hotel according to claim 11 TVs, is characterized in that, described second acquisition device comprises as lower device:
Second calling device: for sending call instruction to the second information source, wherein, described call instruction comprises guest identification's information;
Second receiving system: that the second information source returns according to call instruction with second guest's information that is guest identification's information matches for receiving;
Second guest's information of described coupling comprises: the guest's information corresponding to other guest identification's information be associated with the guest identification's information in call instruction.
The information recommendation system of 15. hotel according to claim 11 TVs, is characterized in that, described first generating apparatus comprises as lower device:
First analytical equipment: for analyzing guest's attribute information and/or guest's behavioural information obtains guest's feature;
Second processing unit: for using any one in guest's attribute information, guest's behavioural information and guest's feature or appoint multiple information as the elementary label of guest.
The information recommendation system of 16. hotel according to claim 11 TVs, is characterized in that, described first clustering apparatus comprises as lower device:
First coalignment: for by the classification of elementary for guest tag match in guest's model;
3rd processing unit: for using the set label in described classification as the secondary label corresponding to the elementary label of this guest;
4th processing unit: for using described secondary label as the information in cluster result.
The information recommendation system of 17. hotel according to claim 11 TVs, is characterized in that, also comprise as lower device:
6th acquisition device: for sending destination service to guest.
The information recommendation system of 18. hotel according to claim 17 TVs, is characterized in that, described 6th acquisition device comprises as lower device:
7th acquisition device: for obtain guest client in the sequencing of menu column offer;
First dispensing device: for sending the destination service corresponding with the various menu column according to sequencing successively to client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510402089.9A CN105227971B (en) | 2015-07-09 | 2015-07-09 | A kind of information recommendation method and system of hotel's TV |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510402089.9A CN105227971B (en) | 2015-07-09 | 2015-07-09 | A kind of information recommendation method and system of hotel's TV |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105227971A true CN105227971A (en) | 2016-01-06 |
| CN105227971B CN105227971B (en) | 2019-01-08 |
Family
ID=54996607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510402089.9A Expired - Fee Related CN105227971B (en) | 2015-07-09 | 2015-07-09 | A kind of information recommendation method and system of hotel's TV |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105227971B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812830A (en) * | 2016-03-11 | 2016-07-27 | 传成文化传媒（上海）有限公司 | Recommendation method and system of hotel service content |
| CN105843864A (en) * | 2016-03-17 | 2016-08-10 | 合网络技术（北京）有限公司 | Message pushing method and device |
| CN105956871A (en) * | 2016-04-18 | 2016-09-21 | 上海木爷机器人技术有限公司 | Service information processing method and service information processing system |
| CN107025310A (en) * | 2017-05-17 | 2017-08-08 | 长春嘉诚信息技术股份有限公司 | A kind of automatic news in real time recommends method |
| CN107153659A (en) * | 2016-03-04 | 2017-09-12 | 朱开 | A kind of recommendation method and commending system applied to social networks |
| CN108038732A (en) * | 2017-12-25 | 2018-05-15 | 北京比利信息技术有限公司 | A kind of brand advertising method for running and device |
| CN108156237A (en) * | 2017-12-22 | 2018-06-12 | 平安养老保险股份有限公司 | Product information method for pushing, device, storage medium and computer equipment |
| CN108573390A (en) * | 2017-03-08 | 2018-09-25 | 北京跃盟科技有限公司 | Content method for dynamically processing and system |
| WO2018201330A1 (en) * | 2017-05-03 | 2018-11-08 | 深圳市智晟达科技有限公司 | Method for personalising digital television programmes in hotel and digital television |
| CN109189978A (en) * | 2018-08-27 | 2019-01-11 | 广州酷狗计算机科技有限公司 | The method, apparatus and storage medium of audio search are carried out based on speech message |
| WO2019157652A1 (en) * | 2018-02-13 | 2019-08-22 | 徐璇炫 | Method and device for determining services hotel hosting conference can provide to participants |
| CN111090769A (en) * | 2018-10-24 | 2020-05-01 | 百度在线网络技术（北京）有限公司 | Song recommendation method, device, equipment and computer storage medium |
| CN111125566A (en) * | 2019-12-11 | 2020-05-08 | 贝壳技术有限公司 | Information acquisition method and device, electronic equipment and storage medium |
| CN112612957A (en) * | 2020-12-24 | 2021-04-06 | 北京百度网讯科技有限公司 | Interest point recommendation method, interest point recommendation model training method and device |
| CN113139667A (en) * | 2021-05-07 | 2021-07-20 | 深圳他米科技有限公司 | Hotel room recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN113361920A (en) * | 2021-06-04 | 2021-09-07 | 上海华客信息科技有限公司 | Hotel service optimization index recommendation method, system, equipment and storage medium |
| CN113362105A (en) * | 2021-06-01 | 2021-09-07 | 北京十一贝科技有限公司 | User label forming method, device and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071424A (en) * | 2006-06-23 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Personalized information push system and method |
| CN102158365A (en) * | 2011-05-20 | 2011-08-17 | 北京邮电大学 | User clustering method and system in weblog mining |
| CN103067756A (en) * | 2011-10-20 | 2013-04-24 | 安美世纪（北京）科技有限公司 | System and method for Portal homepage compulsive displaying |
| CN103488788A (en) * | 2011-12-27 | 2014-01-01 | 奇智软件（北京）有限公司 | Method and device for recommending applications automatically |
| US8812503B2 (en) * | 2010-02-15 | 2014-08-19 | Sony Corporation | Information processing device, method and program |
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
-
2015
- 2015-07-09 CN CN201510402089.9A patent/CN105227971B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071424A (en) * | 2006-06-23 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Personalized information push system and method |
| US8812503B2 (en) * | 2010-02-15 | 2014-08-19 | Sony Corporation | Information processing device, method and program |
| CN102158365A (en) * | 2011-05-20 | 2011-08-17 | 北京邮电大学 | User clustering method and system in weblog mining |
| CN103067756A (en) * | 2011-10-20 | 2013-04-24 | 安美世纪（北京）科技有限公司 | System and method for Portal homepage compulsive displaying |
| CN103488788A (en) * | 2011-12-27 | 2014-01-01 | 奇智软件（北京）有限公司 | Method and device for recommending applications automatically |
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153659A (en) * | 2016-03-04 | 2017-09-12 | 朱开 | A kind of recommendation method and commending system applied to social networks |
| CN105812830A (en) * | 2016-03-11 | 2016-07-27 | 传成文化传媒（上海）有限公司 | Recommendation method and system of hotel service content |
| CN105812830B (en) * | 2016-03-11 | 2018-11-13 | 传成文化传媒（上海）有限公司 | The recommendation method and system of hotel service content |
| CN105843864A (en) * | 2016-03-17 | 2016-08-10 | 合网络技术（北京）有限公司 | Message pushing method and device |
| CN105956871A (en) * | 2016-04-18 | 2016-09-21 | 上海木爷机器人技术有限公司 | Service information processing method and service information processing system |
| CN108573390A (en) * | 2017-03-08 | 2018-09-25 | 北京跃盟科技有限公司 | Content method for dynamically processing and system |
| WO2018201330A1 (en) * | 2017-05-03 | 2018-11-08 | 深圳市智晟达科技有限公司 | Method for personalising digital television programmes in hotel and digital television |
| CN107025310A (en) * | 2017-05-17 | 2017-08-08 | 长春嘉诚信息技术股份有限公司 | A kind of automatic news in real time recommends method |
| CN108156237A (en) * | 2017-12-22 | 2018-06-12 | 平安养老保险股份有限公司 | Product information method for pushing, device, storage medium and computer equipment |
| CN108156237B (en) * | 2017-12-22 | 2020-07-31 | 平安养老保险股份有限公司 | Product information pushing method and device, storage medium and computer equipment |
| CN108038732A (en) * | 2017-12-25 | 2018-05-15 | 北京比利信息技术有限公司 | A kind of brand advertising method for running and device |
| WO2019157652A1 (en) * | 2018-02-13 | 2019-08-22 | 徐璇炫 | Method and device for determining services hotel hosting conference can provide to participants |
| CN109189978A (en) * | 2018-08-27 | 2019-01-11 | 广州酷狗计算机科技有限公司 | The method, apparatus and storage medium of audio search are carried out based on speech message |
| CN109189978B (en) * | 2018-08-27 | 2020-06-30 | 广州酷狗计算机科技有限公司 | Method, device and storage medium for audio search based on voice message |
| CN111090769A (en) * | 2018-10-24 | 2020-05-01 | 百度在线网络技术（北京）有限公司 | Song recommendation method, device, equipment and computer storage medium |
| CN111125566A (en) * | 2019-12-11 | 2020-05-08 | 贝壳技术有限公司 | Information acquisition method and device, electronic equipment and storage medium |
| CN111125566B (en) * | 2019-12-11 | 2021-08-31 | 贝壳找房(北京)科技有限公司 | Information acquisition method and device, electronic equipment and storage medium |
| CN112612957A (en) * | 2020-12-24 | 2021-04-06 | 北京百度网讯科技有限公司 | Interest point recommendation method, interest point recommendation model training method and device |
| CN112612957B (en) * | 2020-12-24 | 2023-09-29 | 北京百度网讯科技有限公司 | Recommendation method of interest points and training method and device of recommendation model of interest points |
| CN113139667A (en) * | 2021-05-07 | 2021-07-20 | 深圳他米科技有限公司 | Hotel room recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN113139667B (en) * | 2021-05-07 | 2024-02-20 | 深圳他米科技有限公司 | Hotel room recommending method, device, equipment and storage medium based on artificial intelligence |
| CN113362105A (en) * | 2021-06-01 | 2021-09-07 | 北京十一贝科技有限公司 | User label forming method, device and computer readable storage medium |
| CN113362105B (en) * | 2021-06-01 | 2024-02-02 | 北京十一贝科技有限公司 | User tag forming method, apparatus and computer readable storage medium |
| CN113361920A (en) * | 2021-06-04 | 2021-09-07 | 上海华客信息科技有限公司 | Hotel service optimization index recommendation method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105227971B (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105227971A (en) | The information recommendation method of a kind of hotel TV and system | |
| CN105046600A (en) | Personalized information recommendation method and system of televisions for hotels | |
| CN107424043B (en) | Product recommendation method and device and electronic equipment | |
| CN105812830B (en) | The recommendation method and system of hotel service content | |
| CN105046601A (en) | User data processing method and system | |
| US11042590B2 (en) | Methods, systems and techniques for personalized search query suggestions | |
| WO2019056661A1 (en) | Search term pushing method and device, and terminal | |
| EP3873065B1 (en) | Content recommendation method, mobile terminal, and server | |
| US20160239501A1 (en) | Information search method, device, server and storage medium | |
| US9015158B2 (en) | Contents creating device and contents creating method | |
| US11080287B2 (en) | Methods, systems and techniques for ranking blended content retrieved from multiple disparate content sources | |
| CN102073699A (en) | Method, device and equipment for improving search result based on user behaviors | |
| CN103218355A (en) | Method and device for generating tags for user | |
| CN103064880B (en) | A kind of methods, devices and systems providing a user with website selection based on search information | |
| US11899728B2 (en) | Methods, systems and techniques for ranking personalized and generic search query suggestions | |
| US11232522B2 (en) | Methods, systems and techniques for blending online content from multiple disparate content sources including a personal content source or a semi-personal content source | |
| US20140136517A1 (en) | Apparatus And Methods for Providing Search Results | |
| KR101559719B1 (en) | Auto-learning system and method for derive effective marketing | |
| CN111191133B (en) | Service search processing method, device and equipment | |
| US11836169B2 (en) | Methods, systems and techniques for providing search query suggestions based on non-personal data and user personal data according to availability of user personal data | |
| CN111191112A (en) | Electronic reading data processing method, device and storage medium | |
| US20140129634A1 (en) | Social media-based content recommendation apparatus | |
| KR102322668B1 (en) | Systme for providing multi-platform service for stimulating creative activity of contents creator | |
| CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
| KR20140006516A (en) | System and method for providing location based contents service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190108 Termination date: 20200709 |